Classification of Ear Biometric Data using Support Vector Machine

In this paper, a method to recognize persons using ear biometrics has been proposed. We propose a method to classify ears based on supervised learning using Support Vector Machine (SVM). For this, ear has been considered as a planar surface of irregular shape. The shape based features like distribution of area, moment of inertia (MI) with respect to minor and major axis and radius of gyration with respect to minor and major axis are considered.

A database of 605 ears were considered in the development of the model. SVM was able to classify the ears into three groups. A recognition accuracy of 93% has been recorded. The clusters so formed were analyzed for precision, recall, f-measure and kappa statistics. The results showed that the SVM is a robust method.